From 5ae8b7d071bb572daa1f54bd035d754054c7e150 Mon Sep 17 00:00:00 2001
From: "hugo.pradier2" <hugo.pradier2@etu.uca.fr>
Date: Wed, 19 Jun 2024 08:18:14 +0200
Subject: [PATCH] debut prediction

---
 .gitignore                   |  1 +
 frontend/pages/prediction.py | 56 ++++++++++++++++++++++++++++++++++++
 2 files changed, 57 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 frontend/pages/prediction.py

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..b694934
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+.venv
\ No newline at end of file
diff --git a/frontend/pages/prediction.py b/frontend/pages/prediction.py
new file mode 100644
index 0000000..25c074e
--- /dev/null
+++ b/frontend/pages/prediction.py
@@ -0,0 +1,56 @@
+import streamlit as st
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.linear_model import LogisticRegression
+from sklearn.linear_model import LinearRegression
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import accuracy_score
+from sklearn import datasets
+from sklearn.impute import SimpleImputer  # Add this line
+import pandas as pd
+import numpy as np
+st.header("Prediction")
+
+if "data" in st.session_state:
+    data = st.session_state.data
+
+    with st.form("my_form"):
+        header = st.columns([2,1,2])
+        header[0].subheader("Model")
+        header[1].subheader("Data Name")
+
+        row1 = st.columns([2,1,2])
+        model = row1[0].selectbox("", ["Random Forest Classifier", "Random Forest Regressor", "Logistic Regression", "Linear Regression"])
+        data_name = row1[1].selectbox("", data.columns)
+
+        st.form_submit_button('launch')
+            
+    if model == "Random Forest Classifier":
+        model = RandomForestClassifier()
+    elif model == "Random Forest Regressor":
+        model = RandomForestRegressor()
+    elif model == "Logistic Regression":
+        model = LogisticRegression()
+    elif model == "Linear Regression":
+        model = LinearRegression()
+    
+    x = data.drop(data_name, axis=1)
+    y = data[data_name]
+    
+    # Convert categorical data to numerical values
+    x = pd.get_dummies(x)
+    
+    # Handle missing values
+    imputer = SimpleImputer()
+    x = imputer.fit_transform(x)
+    x = pd.get_dummies(x)
+    
+    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42)
+    model.fit(x_train, y_train)
+    y_pred = model.predict(x_test)
+    if model == "Random Forest Classifier":
+        st.write("Accuracy: ", accuracy_score(y_test, y_pred))
+    elif model == "Random Forest Regressor" or model == "Logistic Regression" or model == "Linear Regression":
+        st.write("Mean Squared Error: ", np.mean((y_pred - y_test) ** 2))
+else:
+    st.error("file not loaded")